# hku-mars/FAST-LIVO

A Fast and Tightly-coupled Sparse-Direct LiDAR-Inertial-Visual Odometry (LIVO).

Repository: https://github.com/hku-mars/FAST-LIVO
Canonical: https://ross.abutalabs.com/products/fast-livo
Language: C++
License: GPL-2.0
License Family: copyleft
Topics: 3d-reconstruction, lidar-camera-fusion, lidar-camera-synchronization, sensor-fusion, slam
Last push: 2025-09-12T17:47:07+00:00

## Health v2 (maintenance only)
Score: 51/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 41, release rhythm 35, longevity 100
- inputs: {"age_days": 1644, "days_push": 355, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1631, forks 267 (observed 2026-08-28T04:05:14.020330+00:00)

## What it is
FAST-LIVO is a fast, tightly-coupled sparse-direct LiDAR-Inertial-Visual Odometry system combining a LIO subsystem that registers raw points to an incrementally-built point cloud map and a VIO subsystem that aligns images via direct photometric error minimization. It is a C++/ROS research codebase from HKU MARS, published at IROS 2022, with a successor FAST-LIVO2 available.

## Use cases
- estimate robot trajectory from lidar, camera, and IMU data
- build 3D point cloud maps with color from camera images
- perform real-time odometry for UAV navigation
- fuse lidar and camera measurements in a tightly-coupled SLAM system
- run odometry in degenerate lidar or camera scenarios
- reconstruct colored 3D environments from sensor data

## When to choose
- you need real-time LiDAR-inertial-visual odometry with direct (feature-less) methods
- you want colored point cloud mapping from lidar-camera fusion
- you are doing UAV state estimation or onboard navigation research
- you work with Livox lidars and ROS on Ubuntu

## When to avoid
- you need a production-supported product rather than research code
- you do not use ROS or Linux
- you want the latest accuracy improvements, in which case FAST-LIVO2 is preferable
- you need a visual SLAM system without a lidar sensor

## Facets
- artifact type: library
- maturity: stable
- function: simulation, computer-vision, image-processing
- domain: robotics, autonomous-vehicles, computer-vision
- platform: cpp
- tags: slam, lidar, odometry, sensor-fusion, point-cloud, visual-inertial-odometry, lidar-inertial-odometry, state-estimation, uav, algorithms, linux, ros

## Member repositories
- hku-mars/FAST-LIVO (main) score 51

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:14.020330+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:47:50.918182+00:00, confidence not recorded.
  - readme: https://github.com/hku-mars/FAST-LIVO (fetched 2026-08-28T04:05:14.020330+00:00, sha 31ab26097de4)
- Data as of 2026-08-30T08:39:29.467469+00:00.